Pengenalan Permukaan Berbasis Sensor IMU Menggunakan Random Forest Classifier
Abstract
Dengan meningkatnya tantangan yang dihadapi oleh robot akibat kemajuan teknologi dan keragaman kasus, input yang diperlukan oleh robot menjadi lebih banyak dan variatif, sehingga tidak dapat diselesaikan hanya dengan if conditional yang sederhana. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan model machine learning yang dapat membantu robot navigasi untuk mengidentifikasi permukaan yang optimal dengan tingkat akurasi yang tinggi. Penelitian ini menggunakan random forest sebagai algoritma machine learning yang termasuk dalam kategori supervised learning untuk menghasilkan prediksi berdasarkan data latih. Data latih di augmentasi dengan data dari yang telah disintesis menggunakan CTGAN, yaitu sebuah metode yang menggunakan jaringan saraf tiruan untuk menghasilkan data tabular heterogen yang mirip dengan data asli. Metode ini juga dapat melindungi privasi data asli dengan menggunakan privasi diferensial dan pembelajaran federasi. Setelah model machine learning dibangun, model diuji dengan data uji yang dibuat. Model machine learning yang berbasis random forest ini menunjukkan kinerja yang baik dengan mencapai akurasi 90% pada prediksi data uji.
Keywords
References
P. Wu, M. Fang, and Z. Ding, "Wall-Following Navigation for Mobile Robot Based on Random
Forest and Genetic Algorithm," in Intelligent Computing Theories and Application, vol. 12837,
D.-S. Huang, K.-H. Jo, J. Li, V. Gribova, and A. Hussain Eds. Cham: Springer International Publishing, 2021, pp. 122-131.
D. Kato et al., "Positioning Error Calibration of Industrial Robots Based on Random Forest," (in
en), International Journal of Automation Technology, vol. 15, no. 5, pp. 581-589, 2021-09-05 2021, doi: 10.20965/ijat.2021.p0581.
J. Zhang, M. Li, Y. Feng, and C. Yang, "Robotic grasp detection based on image processing and random forest," (in en), Multimedia Tools and Applications, vol. 79, no. 3-4, pp. 2427-2446, 01/2020 2020, doi: 10.1007/s11042-019-08302-9.
A. M. Abdulkadium, "A Robot Obstacle Avoidance Method based on Random Forest HTM Cortical Learning Algorithm," Webology, vol. 17, no. 2, pp. 788-803, 2020-12-21 2020, doi: 10.14704/WEB/V17I2/WEB17067.
Z. Gu and Q. Li, "Half-Voting Random Forest Algorithm and Its Application in Indoor Pedestrian Navigation," (in en), Automatic Control and Computer Sciences, vol. 54, no. 2, pp.100-109, 03/2020 2020, doi: 10.3103/S0146411620020054.
S. Badar ud din Tahir, A. Jalal, and M. Batool, "Wearable Sensors for Activity Analysis using SMO-based Random Forest over Smart home and Sports Datasets," in 2020 3rd International Conference on Advancements in Computational Sciences (ICACS), 2/2020 2020, Lahore, Pakistan: IEEE, pp. 1-6, doi: 10.1109/ICACS47775.2020.9055944.
D. Ko, S.-H. Choi, S. Ahn, and Y.-H. Choi, "Robust Indoor Localization Methods Using Random Forest-Based Filter against MAC Spoofing Attack," (in en), Sensors, vol. 20, no. 23, p. 6756, 2020-11-26 2020.
C. A. Crespo-Santiago and S. d. l. C. D. Cosme, "Waterfall method: a necessary tool for implementing library projects," HETS Online Journal, vol. 1, no. 2, pp. 86-99, 2011 2011.
H. J. Adèr, G. J. Mellenbergh, and D. J. Hand, Advising on research methods: a consultant's companion. Huizen: Johannes van Kessel (in eng), 2008, p. 574.
C. Chen, W. Chai, A. K. Nasir, and H. Roth, "Low cost IMU based indoor mobile robot navigation with the assist of odometry and Wi-Fi using dynamic constraints," in 2012 IEEE/ION Position, Location and Navigation Symposium - PLANS 2012, 04/2012 2012, Myrtle Beach, SC, USA: IEEE, pp. 1274-1279, doi: 10.1109/PLANS.2012.6236984.
A. Chatterjee, A. Rakshit, and N. N. Singh, Vision based autonomous robot navigation: algorithms and implementations (Studies in computational intelligence, no. 455). Heidelberg ; New York: Springer, 2013, p. 226.
P. Domingos, The master algorithm: how the quest for the ultimate learning machine will remake our world. New York: Basic Books, a member of the Perseus Books Group, 2015, p. 329.
V. Nationen, V. Nationen and V. Nationen, Eds. Impact on data quality (Statistical data editing, no. United Nations Statistical Commission ... ; 3). New York, NY: United Nations (in eng), 2006, p. 366.
O. Juwita, N. D. Aprilianti, K. Wibowo, and M. F. Najib, "Pengolahan Sampah Plastik Menjadi Eco Paving Block di Desa Pekauman Bondowoso," JAST : Jurnal Aplikasi Sains dan Teknologi, vol. 8, no. 1, pp. 73-81, 2024-07-10 2024, doi: 10.33366/jast.v8i1.5904.
DOI: https://doi.org/10.30591/smartcomp.v14i1.7347
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution 4.0 International License.
========================================================================
Smart Comp Indexed By:
![]() | ![]() | ![]() | ![]() |
![]() | ![]() | ![]() |
This work is licensed under a Creative Commons Attribution 4.0 International License.















